Vito Sansevero
32cc071d07
Apply now finds the legacy rows of the same physical file however its root is reached. The roots are real paths while the monitor links under the directory it watches, so a symlinked or junctioned root, subst or a mapped drive used to hide the monitor's row and Apply added a second, differently linked row. Same-name rows are resolved to their physical identity (normcase(realpath), else samefile); the dependency fingerprint covers all of them, two rows refuse the choice, one row is enriched under the ingester's compatible-only rules, and a same-name row the request did not classify is a changed association. Apply re-verifies only what the decision depends on: the bytes are still ambiguous and still offer the chosen candidate. A resolver change that rewords the reason or reorders candidates leaves pending items applicable. The resolver version is one constant in prompt_pair_resolver, shared by ingestion provenance and Needs review. The transaction's byte check receives the re-hashed digest (or the body's for Leave unresolved), every Apply refusal branch is tested with zero writes, and the root listing and realpath calls run on a worker thread.
1059 lines
43 KiB
Python
1059 lines
43 KiB
Python
"""Needs review decisions and queue reads (#249 E3).
|
|
|
|
The queue lists pending items oldest first behind an HMAC cursor bound to the
|
|
storage epoch and the review index revision; ``total`` is the exact pending
|
|
count. A decision is explicit: Apply links the chosen sampler's pair only
|
|
under the ingester's compatible rules and only for the current, re-hashed
|
|
bytes of the reviewed file, in one transaction with its decision row; Leave
|
|
unresolved records the decision and links nothing. Responses never carry a
|
|
server path.
|
|
"""
|
|
|
|
import json
|
|
import ntpath
|
|
import os
|
|
import posixpath
|
|
import sqlite3
|
|
from pathlib import Path
|
|
from unittest.mock import patch
|
|
|
|
try:
|
|
from tests.test_review import (
|
|
ReviewTestCase,
|
|
ambiguous_graph,
|
|
digest,
|
|
write_png,
|
|
)
|
|
except ImportError: # discovered with tests/ as the top-level directory
|
|
from test_review import ReviewTestCase, ambiguous_graph, digest, write_png
|
|
|
|
from database.review_schema import canonical_evidence, evidence_digest
|
|
from py.config import GalleryConfig
|
|
from utils import review_capture as review_capture_module
|
|
from utils.media_capture import CaptureChanged, FileFacts
|
|
from utils.hashing import generate_prompt_hash
|
|
|
|
try: # guarded so a missing module fails assertions, not test loading
|
|
from py.api import review as review_api
|
|
except ImportError:
|
|
review_api = None
|
|
|
|
ITEMS_URL = "/prompt_manager/review/items"
|
|
# Every table a decision may touch; compared whole before and after.
|
|
WRITE_TABLES = (
|
|
"prompts",
|
|
"generated_images",
|
|
"prompt_pairs",
|
|
"image_prompt_pairs",
|
|
"media_review_items",
|
|
"media_review_decisions",
|
|
"media_review_metadata",
|
|
)
|
|
|
|
|
|
class ReviewRoutesTestCase(ReviewTestCase):
|
|
def _require_routes(self):
|
|
self.assertIsNotNone(review_api, "py.api.review is not implemented")
|
|
|
|
def _ambiguous(self, name="two.png", positives=("cat", "dog"), color=(255, 0, 0)):
|
|
path = self.output_dir / name
|
|
path.parent.mkdir(parents=True, exist_ok=True)
|
|
write_png(path, prompt=ambiguous_graph(*positives), color=color)
|
|
return path
|
|
|
|
def _record(self, path):
|
|
self._roots()
|
|
outcome = self.api.record_review_file(str(path))
|
|
self.assertIn(outcome, ("recorded", "limited"), outcome)
|
|
return outcome
|
|
|
|
async def _json(self, method, url, **kwargs):
|
|
resp = await self.client.request(method, url, **kwargs)
|
|
data = await resp.json()
|
|
self.responses.append(data)
|
|
return resp.status, data
|
|
|
|
async def asyncSetUp(self):
|
|
await super().asyncSetUp()
|
|
self.responses = []
|
|
|
|
async def _list(self, query=""):
|
|
status, data = await self._json("GET", ITEMS_URL + query)
|
|
self.assertEqual(status, 200, data)
|
|
return data
|
|
|
|
async def _detail(self, item_id):
|
|
status, data = await self._json("GET", f"{ITEMS_URL}/{item_id}")
|
|
self.assertEqual(status, 200, data)
|
|
return data
|
|
|
|
async def _observe(self, target):
|
|
status, data = await self._json(
|
|
"POST", "/prompt_manager/image-annotations/observe", json={"target": target}
|
|
)
|
|
self.assertEqual(status, 200, data)
|
|
return data
|
|
|
|
async def _open(self):
|
|
"""The first pending item, its detail and a fresh capture of its file."""
|
|
listed = await self._list()
|
|
item = listed["items"][0]
|
|
detail = await self._detail(item["id"])
|
|
observed = await self._observe(item["target"])
|
|
return item, detail, observed
|
|
|
|
@staticmethod
|
|
def _candidate(detail, positive):
|
|
return next(
|
|
c for c in detail["candidates"] if c["positive"]["text"] == positive
|
|
)
|
|
|
|
def _body(self, detail, observed, choice):
|
|
return {
|
|
"expected_epoch": observed["library_epoch"],
|
|
"expected_revision": detail["revision"],
|
|
"capture_token": observed["capture"]["token"],
|
|
"sha256": observed["capture"]["sha256"],
|
|
"dependency_fingerprint": detail["dependency_fingerprint"],
|
|
"choice": choice,
|
|
}
|
|
|
|
async def _decide(self, item_id, body):
|
|
return await self._json("POST", f"{ITEMS_URL}/{item_id}/decision", json=body)
|
|
|
|
def _snapshot(self):
|
|
conn = self.api.db.model.get_connection()
|
|
return {
|
|
table: [tuple(row) for row in conn.execute(f"SELECT * FROM {table}")]
|
|
for table in WRITE_TABLES
|
|
}
|
|
|
|
def _decisions(self):
|
|
conn = self.api.db.model.get_connection()
|
|
return [
|
|
dict(row)
|
|
for row in conn.execute(
|
|
"SELECT * FROM media_review_decisions ORDER BY decision_revision"
|
|
)
|
|
]
|
|
|
|
def _no_paths(self):
|
|
for data in self.responses:
|
|
text = canonical_evidence({"r": data})
|
|
self.assertNotIn(self.tmpdir, text)
|
|
self.assertNotIn(self.tmpdir.replace(os.sep, "/"), text)
|
|
self.assertNotIn(os.path.normcase(self.tmpdir), text)
|
|
|
|
|
|
class TestQueueReads(ReviewRoutesTestCase):
|
|
async def test_total_is_exact_pending_count(self):
|
|
self._require_routes()
|
|
for index in range(3):
|
|
self._record(self._ambiguous(f"f{index}.png", color=(index, 0, 0)))
|
|
page = await self._list("?limit=1")
|
|
self.assertEqual(page["total"], 3)
|
|
self.assertEqual(len(page["items"]), 1)
|
|
seen = [page["items"][0]["id"]]
|
|
while page["next_cursor"]:
|
|
page = await self._list(f"?limit=1&cursor={page['next_cursor']}")
|
|
self.assertEqual(page["total"], 3)
|
|
seen.extend(item["id"] for item in page["items"])
|
|
rows = self._items()
|
|
self.assertEqual(seen, [row["id"] for row in rows])
|
|
item = (await self._list())["items"][0]
|
|
self.assertEqual(
|
|
set(item),
|
|
{
|
|
"id",
|
|
"state",
|
|
"revision",
|
|
"created_at",
|
|
"filename",
|
|
"target",
|
|
"unavailable",
|
|
"candidate_count",
|
|
"limited",
|
|
},
|
|
)
|
|
self.assertEqual(
|
|
(item["state"], item["revision"], item["filename"]),
|
|
("pending", 0, "f0.png"),
|
|
)
|
|
self.assertEqual(item["candidate_count"], 2)
|
|
self.assertIs(item["unavailable"], False)
|
|
self.assertEqual(item["target"]["path"], "f0.png")
|
|
self.assertEqual(item["target"]["root_index"], 0)
|
|
conn = self.api.db.model.get_connection()
|
|
with conn:
|
|
conn.execute(
|
|
"UPDATE media_review_items SET state='selected', revision=1 "
|
|
"WHERE id=?",
|
|
(seen[0],),
|
|
)
|
|
conn.execute(
|
|
"UPDATE media_review_items SET state='unresolved', revision=1 "
|
|
"WHERE id=?",
|
|
(seen[1],),
|
|
)
|
|
page = await self._list()
|
|
self.assertEqual(page["total"], 1)
|
|
self.assertEqual([i["id"] for i in page["items"]], [seen[2]])
|
|
self.assertIsNone(page["next_cursor"])
|
|
self._no_paths()
|
|
|
|
async def test_empty_queue_and_limit_validation(self):
|
|
self._require_routes()
|
|
page = await self._list()
|
|
self.assertEqual(
|
|
(page["success"], page["total"], page["items"], page["next_cursor"]),
|
|
(True, 0, [], None),
|
|
)
|
|
self.assertEqual(page["library_epoch"], self.api.db.get_execution_epoch())
|
|
for query in ("?limit=0", "?limit=41", "?limit=abc", "?limit=-1", "?limit=1.5"):
|
|
status, data = await self._json("GET", ITEMS_URL + query)
|
|
self.assertEqual(status, 400, query)
|
|
self.assertFalse(data["success"])
|
|
status, data = await self._json("GET", ITEMS_URL + "?cursor=" + "x" * 5000)
|
|
self.assertEqual(status, 400)
|
|
|
|
async def test_cursor_invalidated_by_decision_and_restore(self):
|
|
self._require_routes()
|
|
for index in range(3):
|
|
self._record(self._ambiguous(f"f{index}.png", color=(index, 0, 0)))
|
|
first = await self._list("?limit=1")
|
|
cursor = first["next_cursor"]
|
|
self.assertTrue(cursor)
|
|
# Tampered: one character changed, or a cursor of another shape.
|
|
broken = ("A" if cursor[5] != "A" else "B").join((cursor[:5], cursor[6:]))
|
|
status, data = await self._json("GET", f"{ITEMS_URL}?cursor={broken}")
|
|
self.assertEqual(status, 400, data)
|
|
# A decision moves the review index revision: the old cursor is stale.
|
|
item, detail, observed = await self._open()
|
|
status, data = await self._decide(
|
|
item["id"], {**self._body(detail, observed, "unresolved")}
|
|
)
|
|
self.assertEqual(status, 200, data)
|
|
status, data = await self._json("GET", f"{ITEMS_URL}?limit=1&cursor={cursor}")
|
|
self.assertEqual(status, 409, data)
|
|
self.assertEqual(data["code"], "review-conflict")
|
|
self.assertEqual(data["total"], 2)
|
|
fresh = (await self._list("?limit=1"))["next_cursor"]
|
|
conn = self.api.db.model.get_connection()
|
|
with conn: # a restore replaces the storage epoch
|
|
conn.execute(
|
|
"UPDATE execution_history_metadata SET "
|
|
"storage_epoch='00000000-0000-4000-8000-000000000000'"
|
|
)
|
|
status, data = await self._json("GET", f"{ITEMS_URL}?limit=1&cursor={fresh}")
|
|
self.assertEqual(status, 409, data)
|
|
self.assertEqual(data["code"], "storage-changed")
|
|
self.assertEqual(data["library_epoch"], "00000000-0000-4000-8000-000000000000")
|
|
self._no_paths()
|
|
|
|
async def test_detail_size_cap_and_limited_item_has_no_candidates(self):
|
|
self._require_routes()
|
|
self._roots()
|
|
limited = self.output_dir / "limited.png"
|
|
write_png(
|
|
limited,
|
|
parameters=(
|
|
"cat\nNegative prompt: blur\nNegative prompt: noise\n"
|
|
"Steps: 20, Sampler: Euler"
|
|
),
|
|
)
|
|
self.assertEqual(self.api.record_review_file(str(limited)), "limited")
|
|
self._record(self._ambiguous("two.png"))
|
|
items = (await self._list())["items"]
|
|
self.assertEqual([i["limited"] for i in items], [True, False])
|
|
detail = await self._detail(items[0]["id"])
|
|
self.assertEqual((detail["limited"], detail["candidates"]), (True, []))
|
|
self.assertEqual(detail["candidate_count"], 0)
|
|
detail = await self._detail(items[1]["id"])
|
|
self.assertEqual(len(detail["candidates"]), 2)
|
|
candidate = self._candidate(detail, "cat")
|
|
self.assertEqual(
|
|
set(candidate),
|
|
{"hash", "sampler_id", "state", "reason", "label", "positive", "negative"},
|
|
)
|
|
self.assertEqual(candidate["positive"], {"text": "cat"})
|
|
self.assertEqual(candidate["negative"], {"text": "bad"})
|
|
self.assertEqual(candidate["state"], "resolved")
|
|
self.assertEqual(candidate["label"], "cat / bad")
|
|
self.assertEqual(detail["sha256"], digest(self.output_dir / "two.png"))
|
|
self.assertRegex(detail["dependency_fingerprint"], r"^[0-9a-f]{64}$")
|
|
with patch.object(review_api, "MAX_DETAIL_BYTES", 200):
|
|
capped = await self._detail(items[1]["id"])
|
|
self.assertEqual((capped["limited"], capped["candidates"]), (True, []))
|
|
self.assertEqual(capped["id"], items[1]["id"])
|
|
for missing in ("00000000-0000-4000-8000-000000000000", "not-a-uuid"):
|
|
status, data = await self._json("GET", f"{ITEMS_URL}/{missing}")
|
|
self.assertEqual(status, 404, data)
|
|
self.assertFalse(data["success"])
|
|
self._no_paths()
|
|
|
|
async def test_label_uses_library_title_of_a_saved_prompt(self):
|
|
self._require_routes()
|
|
prompt_id = self.api.db.save_prompt(
|
|
"cat", prompt_hash=generate_prompt_hash("cat")
|
|
)
|
|
conn = self.api.db.model.get_connection()
|
|
with conn:
|
|
conn.execute(
|
|
"INSERT INTO prompt_library_state(prompt_id,title) VALUES(?,?)",
|
|
(prompt_id, "Dunes"),
|
|
)
|
|
self._record(self._ambiguous("two.png"))
|
|
item = (await self._list())["items"][0]
|
|
detail = await self._detail(item["id"])
|
|
self.assertEqual(self._candidate(detail, "cat")["label"], "Dunes / bad")
|
|
self.assertEqual(self._candidate(detail, "dog")["label"], "dog / bad")
|
|
|
|
async def test_unavailable_when_no_current_root_lists_the_file(self):
|
|
self._require_routes()
|
|
self._record(self._ambiguous("two.png"))
|
|
other = self.output_dir / "elsewhere"
|
|
other.mkdir()
|
|
from py.config import GalleryConfig
|
|
|
|
GalleryConfig.MONITORING_DIRECTORIES = [self._root(other)]
|
|
item = (await self._list())["items"][0]
|
|
self.assertEqual(
|
|
(item["unavailable"], item["target"], item["filename"]),
|
|
(True, None, "two.png"),
|
|
)
|
|
detail = await self._detail(item["id"])
|
|
self.assertIs(detail["unavailable"], True)
|
|
self._no_paths()
|
|
|
|
def test_target_formatting_keeps_the_recorded_spelling_on_windows(self):
|
|
self._require_routes()
|
|
spelled = "C:\\Out\\Sub\\Image_0001.PNG"
|
|
locator = ntpath.normcase(spelled)
|
|
found = review_api.format_review_target(
|
|
spelled, locator, [(0, "D:\\Other"), (1, "C:\\Out")], pathmod=ntpath
|
|
)
|
|
self.assertEqual(found, (1, "Sub/Image_0001.PNG"))
|
|
self.assertIsNone(
|
|
review_api.format_review_target(
|
|
spelled, locator, [(0, "C:\\Outer")], pathmod=ntpath
|
|
)
|
|
)
|
|
# A recorded spelling that no longer folds to the locator is refused.
|
|
self.assertIsNone(
|
|
review_api.format_review_target(
|
|
spelled, "c:\\out\\sub\\other.png", [(0, "C:\\Out")], pathmod=ntpath
|
|
)
|
|
)
|
|
self.assertEqual(
|
|
review_api.format_review_target(
|
|
"/out/a/b.png", "/out/a/b.png", [(0, "/out")], pathmod=posixpath
|
|
),
|
|
(0, "a/b.png"),
|
|
)
|
|
|
|
|
|
class TestDecisions(ReviewRoutesTestCase):
|
|
async def test_apply_candidate_links_pair_and_records_decision_atomically(self):
|
|
self._require_routes()
|
|
path = self._ambiguous("two.png")
|
|
self._record(path)
|
|
revision = self._review_revision()
|
|
item, detail, observed = await self._open()
|
|
cat = self._candidate(detail, "cat")
|
|
before = self._snapshot()
|
|
# A failure after the link rolls the link back with everything else.
|
|
with patch.object(
|
|
type(self.api.db),
|
|
"_insert_review_decision",
|
|
side_effect=sqlite3.OperationalError("disk I/O error at /secret/path"),
|
|
):
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual(status, 500, data)
|
|
self.assertEqual(data["code"], "decision-failed")
|
|
self.assertNotIn("secret", data["error"])
|
|
self.assertEqual(self._snapshot(), before)
|
|
|
|
# A failed decision keeps its capture for the retry.
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual(status, 200, data)
|
|
self.assertTrue(data["success"])
|
|
self.assertEqual(data["total"], 0)
|
|
self.assertEqual(
|
|
(data["item"]["id"], data["item"]["state"], data["item"]["revision"]),
|
|
(item["id"], "selected", 1),
|
|
)
|
|
conn = self.api.db.model.get_connection()
|
|
image = conn.execute(
|
|
"SELECT gi.id, p.text FROM generated_images gi "
|
|
"JOIN prompts p ON p.id=gi.prompt_id WHERE gi.image_path=?",
|
|
(str(path),),
|
|
).fetchone()
|
|
self.assertEqual(image[1], "cat")
|
|
pair = conn.execute(
|
|
"SELECT pp.id, p.text, n.text FROM prompt_pairs pp "
|
|
"JOIN prompts p ON p.id=pp.positive_prompt_id "
|
|
"JOIN prompts n ON n.id=pp.negative_prompt_id"
|
|
).fetchall()
|
|
self.assertEqual([tuple(row)[1:] for row in pair], [("cat", "bad")])
|
|
self.assertEqual(data["pair"]["id"], pair[0][0])
|
|
self.assertEqual(data["pair"]["image_id"], image[0])
|
|
links = self.api.db.get_image_prompt_pairs(image[0])
|
|
self.assertEqual(len(links), 1)
|
|
provenance = links[0]["provenance"]
|
|
self.assertEqual(provenance["kind"], "user-selection")
|
|
self.assertEqual(provenance["candidate_hash"], cat["hash"])
|
|
self.assertEqual(provenance["reviewed_digest"], digest(path))
|
|
self.assertEqual(provenance["resolver_version"], 1)
|
|
self.assertEqual(provenance["positive"]["text"], "cat")
|
|
(decision,) = self._decisions()
|
|
self.assertEqual(provenance["decision_id"], decision["id"])
|
|
self.assertEqual(
|
|
(
|
|
decision["item_id"],
|
|
decision["decision_revision"],
|
|
decision["outcome"],
|
|
decision["candidate_hash"],
|
|
decision["pair_id"],
|
|
decision["image_id"],
|
|
),
|
|
(item["id"], 1, "selected", cat["hash"], pair[0][0], image[0]),
|
|
)
|
|
self.assertEqual(self._review_revision(), revision + 1)
|
|
self.assertEqual((await self._list())["total"], 0)
|
|
self.assertEqual(self._capture_files(), [])
|
|
self._no_paths()
|
|
|
|
async def test_apply_conflicting_legacy_owner_returns_association_conflict_with_zero_writes( # noqa: E501
|
|
self,
|
|
):
|
|
self._require_routes()
|
|
path = self._ambiguous("two.png")
|
|
# The monitor's fallback link: the file is linked to "cat" already.
|
|
prompt_id = self.api.db.save_prompt(
|
|
"cat", prompt_hash=generate_prompt_hash("cat")
|
|
)
|
|
image_id = self.api.db.link_image_to_prompt(prompt_id, str(path))
|
|
self._record(path)
|
|
item, detail, observed = await self._open()
|
|
before = self._snapshot()
|
|
dog = self._candidate(detail, "dog")
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, dog["hash"])
|
|
)
|
|
self.assertEqual(status, 409, data)
|
|
self.assertEqual(data["code"], "association-conflict")
|
|
self.assertIn("linked", data["error"])
|
|
self.assertEqual(self._snapshot(), before)
|
|
# The compatible choice reuses the existing image row.
|
|
cat = self._candidate(detail, "cat")
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual(status, 200, data)
|
|
self.assertEqual(data["pair"]["image_id"], image_id)
|
|
conn = self.api.db.model.get_connection()
|
|
self.assertEqual(
|
|
conn.execute("SELECT COUNT(*) FROM generated_images").fetchone()[0], 1
|
|
)
|
|
self._no_paths()
|
|
|
|
async def test_changed_dependencies_are_an_association_conflict(self):
|
|
self._require_routes()
|
|
path = self._ambiguous("two.png")
|
|
self._record(path)
|
|
item, detail, observed = await self._open()
|
|
# Another writer links the file after the detail was read.
|
|
prompt_id = self.api.db.save_prompt(
|
|
"cat", prompt_hash=generate_prompt_hash("cat")
|
|
)
|
|
self.api.db.link_image_to_prompt(prompt_id, str(path))
|
|
before = self._snapshot()
|
|
cat = self._candidate(detail, "cat")
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual(status, 409, data)
|
|
self.assertEqual(data["code"], "association-conflict")
|
|
self.assertNotEqual(
|
|
data["dependency_fingerprint"], detail["dependency_fingerprint"]
|
|
)
|
|
self.assertEqual(self._snapshot(), before)
|
|
|
|
async def test_leave_unresolved_records_decision_and_leaves_pending_list(self):
|
|
self._require_routes()
|
|
path = self._ambiguous("two.png")
|
|
self._record(path)
|
|
self._record(self._ambiguous("other.png", color=(0, 0, 9)))
|
|
item, detail, _observed = await self._open()
|
|
body = {
|
|
"expected_epoch": self.api.db.get_execution_epoch(),
|
|
"expected_revision": 0,
|
|
"capture_token": None,
|
|
"sha256": detail["sha256"],
|
|
"dependency_fingerprint": detail["dependency_fingerprint"],
|
|
"choice": "unresolved",
|
|
}
|
|
status, data = await self._decide(item["id"], body)
|
|
self.assertEqual(status, 200, data)
|
|
self.assertEqual(data["item"]["state"], "unresolved")
|
|
self.assertEqual(data["total"], 1)
|
|
self.assertNotIn("pair", data)
|
|
(decision,) = self._decisions()
|
|
self.assertEqual(
|
|
(decision["outcome"], decision["candidate_hash"], decision["pair_id"]),
|
|
("unresolved", None, None),
|
|
)
|
|
conn = self.api.db.model.get_connection()
|
|
for table in ("prompt_pairs", "image_prompt_pairs", "generated_images"):
|
|
self.assertEqual(
|
|
conn.execute(f"SELECT COUNT(*) FROM {table}").fetchone()[0], 0, table
|
|
)
|
|
listed = await self._list()
|
|
self.assertEqual(listed["total"], 1)
|
|
self.assertNotIn(item["id"], [i["id"] for i in listed["items"]])
|
|
# The item still answers its detail, now decided.
|
|
self.assertEqual((await self._detail(item["id"]))["state"], "unresolved")
|
|
self._no_paths()
|
|
|
|
async def test_changed_bytes_or_evidence_reject_apply(self):
|
|
self._require_routes()
|
|
path = self._ambiguous("two.png")
|
|
self._record(path)
|
|
item, detail, observed = await self._open()
|
|
cat = self._candidate(detail, "cat")
|
|
before = self._snapshot()
|
|
|
|
# The file is rewritten after the capture: the re-hash refuses it.
|
|
write_png(path, prompt=ambiguous_graph("cat", "dog"), color=(0, 255, 0))
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual((status, data["code"]), (409, "file-changed"), data)
|
|
self.assertEqual(self._snapshot(), before)
|
|
|
|
# A fresh capture of the new bytes is not the reviewed item's bytes.
|
|
observed = await self._observe(item["target"])
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual((status, data["code"]), (409, "file-changed"), data)
|
|
self.assertEqual(
|
|
self._snapshot()["media_review_items"], before["media_review_items"]
|
|
)
|
|
|
|
# Back to the reviewed bytes, but the evidence they yield has changed.
|
|
write_png(path, prompt=ambiguous_graph("cat", "dog"))
|
|
self.assertEqual(digest(path), detail["sha256"])
|
|
observed = await self._observe(item["target"])
|
|
changed = {
|
|
"state": "ambiguous",
|
|
"reason": "multiple samplers",
|
|
"candidates": [],
|
|
}
|
|
with patch("utils.review_capture.resolve_prompt_pair", return_value=changed):
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual((status, data["code"]), (409, "review-conflict"), data)
|
|
|
|
# A choice that is not one of the item's candidates is refused.
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, "f" * 64)
|
|
)
|
|
self.assertEqual(status, 400, data)
|
|
# A restore since the capture.
|
|
status, data = await self._decide(
|
|
item["id"],
|
|
{
|
|
**self._body(detail, observed, cat["hash"]),
|
|
"expected_epoch": "00000000-0000-4000-8000-000000000000",
|
|
},
|
|
)
|
|
self.assertEqual((status, data["code"]), (409, "storage-changed"), data)
|
|
# A stale revision.
|
|
status, data = await self._decide(
|
|
item["id"],
|
|
{**self._body(detail, observed, cat["hash"]), "expected_revision": 3},
|
|
)
|
|
self.assertEqual((status, data["code"]), (409, "review-conflict"), data)
|
|
# Apply needs a capture; Leave unresolved does not.
|
|
status, data = await self._decide(
|
|
item["id"],
|
|
{**self._body(detail, observed, cat["hash"]), "capture_token": None},
|
|
)
|
|
self.assertEqual(status, 400, data)
|
|
# A capture of another file.
|
|
other = self._ambiguous("other.png", color=(1, 2, 3))
|
|
self._record(other)
|
|
target = {**item["target"], "path": "other.png"}
|
|
foreign = await self._observe(target)
|
|
status, data = await self._decide(
|
|
item["id"],
|
|
{
|
|
**self._body(detail, observed, cat["hash"]),
|
|
"capture_token": foreign["capture"]["token"],
|
|
"sha256": foreign["capture"]["sha256"],
|
|
},
|
|
)
|
|
self.assertEqual((status, data["code"]), (409, "capture-expired"), data)
|
|
self.assertEqual(self._decisions(), [])
|
|
self.assertEqual(self._items()[0]["state"], "pending")
|
|
self._no_paths()
|
|
|
|
async def test_decision_body_validation(self):
|
|
self._require_routes()
|
|
self._record(self._ambiguous("two.png"))
|
|
item, detail, observed = await self._open()
|
|
good = self._body(detail, observed, "unresolved")
|
|
cases = [
|
|
{**good, "extra": 1},
|
|
{k: v for k, v in good.items() if k != "choice"},
|
|
{**good, "expected_epoch": "nope"},
|
|
{**good, "expected_revision": -1},
|
|
{**good, "expected_revision": True},
|
|
{**good, "capture_token": "bad token!"},
|
|
{**good, "sha256": "A" * 64},
|
|
{**good, "dependency_fingerprint": "x"},
|
|
{**good, "choice": "maybe"},
|
|
{**good, "choice": 7},
|
|
{**good, "sha256": "0" * 64},
|
|
]
|
|
for body in cases:
|
|
with self.subTest(body=body):
|
|
status, data = await self._decide(item["id"], body)
|
|
self.assertEqual(status, 400, data)
|
|
self.assertFalse(data["success"])
|
|
status, data = await self._json(
|
|
"POST", f"{ITEMS_URL}/{item['id']}/decision", data=b"[1"
|
|
)
|
|
self.assertEqual(status, 400, data)
|
|
status, data = await self._decide("00000000-0000-4000-8000-000000000000", good)
|
|
self.assertEqual(status, 404, data)
|
|
self.assertEqual(self._decisions(), [])
|
|
|
|
async def test_duplicate_apply_after_commit_is_review_conflict_with_current_state(
|
|
self,
|
|
):
|
|
self._require_routes()
|
|
self._record(self._ambiguous("two.png"))
|
|
item, detail, observed = await self._open()
|
|
cat = self._candidate(detail, "cat")
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual(status, 200, data)
|
|
after = self._snapshot()
|
|
observed = await self._observe(item["target"])
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual(status, 409, data)
|
|
self.assertEqual(data["code"], "review-conflict")
|
|
self.assertEqual(
|
|
(data["item"]["state"], data["item"]["revision"]), ("selected", 1)
|
|
)
|
|
self.assertEqual(data["total"], 0)
|
|
self.assertEqual(self._snapshot(), after)
|
|
self.assertEqual(len(self._decisions()), 1)
|
|
|
|
async def test_tag_save_never_changes_review_item(self):
|
|
self._require_routes()
|
|
self._record(self._ambiguous("two.png"))
|
|
item, _detail, observed = await self._open()
|
|
before = self._snapshot()
|
|
status, data = await self._json(
|
|
"PUT",
|
|
"/prompt_manager/image-annotations/tags",
|
|
json={
|
|
"target": item["target"],
|
|
"capture_token": observed["capture"]["token"],
|
|
"sha256": observed["capture"]["sha256"],
|
|
"expected_epoch": observed["library_epoch"],
|
|
"expected_tag_revision": observed["tag_revision"],
|
|
"tags": ["sunset"],
|
|
},
|
|
)
|
|
self.assertEqual(status, 200, data)
|
|
after = self._snapshot()
|
|
for table in (
|
|
"media_review_items",
|
|
"media_review_decisions",
|
|
"media_review_metadata",
|
|
"generated_images",
|
|
"image_prompt_pairs",
|
|
):
|
|
self.assertEqual(after[table], before[table], table)
|
|
self.assertEqual((await self._list())["total"], 1)
|
|
|
|
async def test_run_and_usage_counts_unchanged(self):
|
|
self._require_routes()
|
|
path = self._ambiguous("two.png")
|
|
prompt_id = self.api.db.save_prompt(
|
|
"cat", prompt_hash=generate_prompt_hash("cat")
|
|
)
|
|
conn = self.api.db.model.get_connection()
|
|
with conn:
|
|
conn.execute(
|
|
"UPDATE prompts SET run_count=5, last_used_at='2026-01-01T00:00:00Z' "
|
|
"WHERE id=?",
|
|
(prompt_id,),
|
|
)
|
|
self._record(path)
|
|
executions = conn.execute(
|
|
"SELECT name FROM sqlite_master WHERE type='table' "
|
|
"AND name LIKE 'execution_%'"
|
|
).fetchall()
|
|
counts = {
|
|
row[0]: conn.execute(f"SELECT COUNT(*) FROM {row[0]}").fetchone()[0]
|
|
for row in executions
|
|
}
|
|
item, detail, observed = await self._open()
|
|
status, data = await self._decide(
|
|
item["id"],
|
|
self._body(detail, observed, self._candidate(detail, "cat")["hash"]),
|
|
)
|
|
self.assertEqual(status, 200, data)
|
|
rows = conn.execute(
|
|
"SELECT text, run_count, last_used_at FROM prompts"
|
|
).fetchall()
|
|
self.assertIn(("cat", 5, "2026-01-01T00:00:00Z"), [tuple(r) for r in rows])
|
|
self.assertEqual({tuple(r)[1] for r in rows if r[0] != "cat"}, {0})
|
|
self.assertEqual(
|
|
{
|
|
name: conn.execute(f"SELECT COUNT(*) FROM {name}").fetchone()[0]
|
|
for name in counts
|
|
},
|
|
counts,
|
|
)
|
|
(pair,) = self.api.db.list_prompt_pairs()["pairs"]
|
|
self.assertEqual(pair["run_count"], 0)
|
|
|
|
async def test_no_absolute_paths_in_responses(self):
|
|
self._require_routes()
|
|
self._record(self._ambiguous("two.png"))
|
|
item, detail, observed = await self._open()
|
|
await self._json("GET", f"{ITEMS_URL}?cursor=bad")
|
|
await self._decide(item["id"], {**self._body(detail, observed, "f" * 64)})
|
|
with patch.object(
|
|
type(self.api.db),
|
|
"review_queue_page",
|
|
side_effect=sqlite3.OperationalError(f"no such table at {self.tmpdir}"),
|
|
):
|
|
status, data = await self._json("GET", ITEMS_URL)
|
|
self.assertEqual((status, data["code"]), (500, "review-failed"))
|
|
with patch.object(
|
|
type(self.api.db),
|
|
"review_item",
|
|
side_effect=sqlite3.OperationalError(f"locked {self.tmpdir}"),
|
|
):
|
|
status, data = await self._json("GET", f"{ITEMS_URL}/{item['id']}")
|
|
self.assertEqual((status, data["code"]), (500, "review-failed"))
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, "unresolved")
|
|
)
|
|
self.assertEqual(status, 200, data)
|
|
self._no_paths()
|
|
|
|
|
|
class TestPhysicalIdentity(ReviewRoutesTestCase):
|
|
"""Apply sees a legacy row of the same file under any spelling (I1).
|
|
|
|
The roots are real paths, but the monitor links a file under the
|
|
directory it watches: a symlink, a Windows junction, ``subst`` or a
|
|
mapped drive reaches the same file under another spelling.
|
|
"""
|
|
|
|
def _monitor_link(self, text, spelled):
|
|
prompt_id = self.api.db.save_prompt(
|
|
text, prompt_hash=generate_prompt_hash(text)
|
|
)
|
|
return self.api.db.link_image_to_prompt(prompt_id, str(spelled))
|
|
|
|
def _rows(self):
|
|
conn = self.api.db.model.get_connection()
|
|
return [
|
|
tuple(row)
|
|
for row in conn.execute(
|
|
"SELECT gi.image_path, p.text FROM generated_images gi "
|
|
"JOIN prompts p ON p.id=gi.prompt_id ORDER BY gi.id"
|
|
)
|
|
]
|
|
|
|
async def _conflict_then_compatible(self, alias_path):
|
|
image_id = self._monitor_link("cat", alias_path)
|
|
item, detail, observed = await self._open()
|
|
before = self._snapshot()
|
|
dog = self._candidate(detail, "dog")
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, dog["hash"])
|
|
)
|
|
self.assertEqual((status, data.get("code")), (409, "association-conflict"))
|
|
self.assertEqual(self._snapshot(), before)
|
|
cat = self._candidate(detail, "cat")
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual(status, 200, data)
|
|
# The monitor's row is enriched; no second row for the same file.
|
|
self.assertEqual(data["pair"]["image_id"], image_id)
|
|
self.assertEqual(self._rows(), [(str(alias_path), "cat")])
|
|
self._no_paths()
|
|
|
|
def _symlinked_root(self):
|
|
alias = Path(self.tmpdir) / "alias-output"
|
|
try:
|
|
os.symlink(str(self.output_dir), str(alias), target_is_directory=True)
|
|
except (OSError, NotImplementedError, AttributeError) as exc:
|
|
self.skipTest(f"symlinks unavailable: {exc}")
|
|
return alias
|
|
|
|
async def test_symlinked_root_legacy_row_is_an_association_conflict(self):
|
|
self._require_routes()
|
|
path = self._ambiguous("two.png")
|
|
alias = self._symlinked_root()
|
|
self._record(path)
|
|
await self._conflict_then_compatible(alias / "two.png")
|
|
|
|
async def test_junction_or_mapped_drive_legacy_row_is_seen(self):
|
|
"""A portable fake of a junction: its realpath is the real root."""
|
|
self._require_routes()
|
|
path = self._ambiguous("two.png")
|
|
self._record(path)
|
|
junction = os.path.join(self.tmpdir, "Junction")
|
|
real = os.path.realpath
|
|
|
|
def fake_realpath(value, *args, **kwargs):
|
|
text = os.fspath(value)
|
|
if os.path.normcase(text).startswith(os.path.normcase(junction)):
|
|
text = str(self.output_dir) + text[len(junction) :]
|
|
return real(text, *args, **kwargs)
|
|
|
|
with patch.object(review_api, "_realpath", side_effect=fake_realpath):
|
|
await self._conflict_then_compatible(os.path.join(junction, "two.png"))
|
|
|
|
async def test_two_rows_under_two_spellings_are_an_association_conflict(self):
|
|
self._require_routes()
|
|
path = self._ambiguous("two.png")
|
|
alias = self._symlinked_root()
|
|
self._monitor_link("cat", alias / "two.png")
|
|
self._monitor_link("cat", path)
|
|
self._record(path)
|
|
item, detail, observed = await self._open()
|
|
before = self._snapshot()
|
|
cat = self._candidate(detail, "cat")
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual((status, data.get("code")), (409, "association-conflict"))
|
|
self.assertEqual(self._snapshot(), before)
|
|
|
|
async def test_same_name_in_another_folder_is_not_the_file(self):
|
|
self._require_routes()
|
|
path = self._ambiguous("two.png")
|
|
other = self.output_dir / "elsewhere" / "two.png"
|
|
other.parent.mkdir(parents=True)
|
|
write_png(other, prompt=ambiguous_graph("cat", "dog"), color=(9, 9, 9))
|
|
self._monitor_link("dog", other)
|
|
self._record(path)
|
|
item, detail, observed = await self._open()
|
|
cat = self._candidate(detail, "cat")
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual(status, 200, data)
|
|
self.assertEqual(
|
|
sorted(self._rows()), sorted([(str(other), "dog"), (str(path), "cat")])
|
|
)
|
|
|
|
async def test_a_new_alias_row_after_the_check_is_a_changed_conflict(self):
|
|
self._require_routes()
|
|
path = self._ambiguous("two.png")
|
|
alias = self._symlinked_root()
|
|
self._record(path)
|
|
item, detail, observed = await self._open()
|
|
cat = self._candidate(detail, "cat")
|
|
# The monitor links the file under its alias after the reviewer opened it.
|
|
self._monitor_link("cat", alias / "two.png")
|
|
before = self._snapshot()
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual((status, data.get("code")), (409, "association-conflict"))
|
|
self.assertNotEqual(
|
|
data["dependency_fingerprint"], detail["dependency_fingerprint"]
|
|
)
|
|
self.assertEqual(self._snapshot(), before)
|
|
|
|
|
|
class TestApplyRefusals(ReviewRoutesTestCase):
|
|
"""Every Apply refusal answers a code and writes nothing (I2, M1, M4)."""
|
|
|
|
async def _opened(self):
|
|
path = self._ambiguous("two.png")
|
|
self._record(path)
|
|
item, detail, observed = await self._open()
|
|
return path, item, detail, observed, self._candidate(detail, "cat")
|
|
|
|
async def _refused(self, item, body, status, code=None):
|
|
before = self._snapshot()
|
|
got, data = await self._decide(item["id"], body)
|
|
self.assertEqual(got, status, data)
|
|
if code is not None:
|
|
self.assertEqual(data["code"], code, data)
|
|
self.assertEqual(self._snapshot(), before)
|
|
self.assertEqual(self._decisions(), [])
|
|
return data
|
|
|
|
async def test_resolver_change_keeps_the_chosen_candidate_applicable(self):
|
|
self._require_routes()
|
|
_path, item, detail, observed, cat = await self._opened()
|
|
real = review_capture_module.resolve_prompt_pair
|
|
|
|
def reworded(metadata):
|
|
resolution = real(metadata)
|
|
return {
|
|
**resolution,
|
|
"reason": "a reworded reason from a newer resolver",
|
|
"candidates": list(reversed(resolution["candidates"])),
|
|
}
|
|
|
|
with (
|
|
patch.object(
|
|
review_capture_module, "resolve_prompt_pair", side_effect=reworded
|
|
),
|
|
patch.object(review_capture_module, "RESOLVER_VERSION", 2),
|
|
):
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual(status, 200, data)
|
|
self.assertEqual(data["item"]["state"], "selected")
|
|
|
|
async def test_chosen_candidate_no_longer_offered_is_a_review_conflict(self):
|
|
self._require_routes()
|
|
_path, item, detail, observed, cat = await self._opened()
|
|
real = review_capture_module.resolve_prompt_pair
|
|
|
|
def without_cat(metadata):
|
|
resolution = real(metadata)
|
|
kept = [
|
|
c
|
|
for c in resolution["candidates"]
|
|
if (c.get("positive") or {}).get("text") != "cat"
|
|
]
|
|
return {**resolution, "candidates": kept * 2}
|
|
|
|
with patch.object(
|
|
review_capture_module, "resolve_prompt_pair", side_effect=without_cat
|
|
):
|
|
await self._refused(
|
|
item,
|
|
self._body(detail, observed, cat["hash"]),
|
|
409,
|
|
"review-conflict",
|
|
)
|
|
|
|
async def test_decision_passes_the_verified_digest(self):
|
|
self._require_routes()
|
|
path, item, detail, observed, cat = await self._opened()
|
|
real = type(self.api.db).decide_review_item
|
|
seen = []
|
|
|
|
def spy(db, **kwargs):
|
|
seen.append(kwargs["sha256"])
|
|
return real(db, **kwargs)
|
|
|
|
with patch.object(type(self.api.db), "decide_review_item", spy):
|
|
status, data = await self._decide(
|
|
item["id"], self._body(detail, observed, cat["hash"])
|
|
)
|
|
self.assertEqual(status, 200, data)
|
|
self.assertEqual(seen, [digest(path)])
|
|
|
|
async def test_expired_capture(self):
|
|
self._require_routes()
|
|
_path, item, detail, observed, cat = await self._opened()
|
|
self.api._captures.release(observed["capture"]["token"])
|
|
await self._refused(
|
|
item, self._body(detail, observed, cat["hash"]), 409, "capture-expired"
|
|
)
|
|
|
|
async def test_a_candidate_that_cannot_be_applied(self):
|
|
self._require_routes()
|
|
_path, item, detail, observed, cat = await self._opened()
|
|
conn = self.api.db.model.get_connection()
|
|
(text,) = conn.execute(
|
|
"SELECT evidence FROM media_review_items WHERE id=?", (item["id"],)
|
|
).fetchone()
|
|
evidence = json.loads(text)
|
|
for candidate in evidence["candidates"]:
|
|
if candidate["hash"] == cat["hash"]:
|
|
candidate["state"] = "unresolved"
|
|
text = canonical_evidence(evidence)
|
|
with conn:
|
|
conn.execute(
|
|
"UPDATE media_review_items SET evidence=?, evidence_hash=? WHERE id=?",
|
|
(text, evidence_digest(text), item["id"]),
|
|
)
|
|
data = await self._refused(item, self._body(detail, observed, cat["hash"]), 400)
|
|
self.assertIn("cannot be applied", data["error"])
|
|
|
|
async def test_leave_unresolved_with_another_digest(self):
|
|
self._require_routes()
|
|
_path, item, detail, observed, _cat = await self._opened()
|
|
body = {
|
|
**self._body(detail, observed, "unresolved"),
|
|
"capture_token": None,
|
|
"sha256": "0" * 64,
|
|
}
|
|
data = await self._refused(item, body, 400)
|
|
self.assertIn("does not match the item", data["error"])
|
|
|
|
async def test_root_no_longer_configured_is_source_changed(self):
|
|
self._require_routes()
|
|
_path, item, detail, observed, cat = await self._opened()
|
|
# Another root takes index 0.
|
|
elsewhere = self.output_dir / "elsewhere"
|
|
elsewhere.mkdir()
|
|
GalleryConfig.MONITORING_DIRECTORIES = [self._root(elsewhere)]
|
|
await self._refused(
|
|
item, self._body(detail, observed, cat["hash"]), 409, "source-changed"
|
|
)
|
|
|
|
async def test_file_no_longer_under_its_root_is_source_changed(self):
|
|
self._require_routes()
|
|
_path, item, detail, observed, cat = await self._opened()
|
|
moved = os.path.join(self.tmpdir, "moved-root")
|
|
real = os.path.realpath
|
|
|
|
def other_root(value, *args, **kwargs):
|
|
if os.path.normcase(os.fspath(value)) == os.path.normcase(
|
|
str(self.output_dir)
|
|
):
|
|
return moved
|
|
return real(value, *args, **kwargs)
|
|
|
|
with patch.object(review_api, "_realpath", side_effect=other_root):
|
|
await self._refused(
|
|
item, self._body(detail, observed, cat["hash"]), 409, "source-changed"
|
|
)
|
|
|
|
async def test_verify_failures(self):
|
|
self._require_routes()
|
|
_path, item, detail, observed, cat = await self._opened()
|
|
store = self.api._captures
|
|
body = self._body(detail, observed, cat["hash"])
|
|
with patch.object(store, "verify", side_effect=CaptureChanged("gone")):
|
|
await self._refused(item, body, 409, "file-changed")
|
|
other = FileFacts(item_locator := self._items()[0]["locator"], "1" * 64, 1, 1)
|
|
with patch.object(store, "verify", return_value=other):
|
|
await self._refused(item, body, 409, "file-changed")
|
|
foreign = FileFacts(item_locator + "x", detail["sha256"], 1, 1)
|
|
with patch.object(store, "verify", return_value=foreign):
|
|
data = await self._refused(item, body, 409, "capture-expired")
|
|
self.assertIn("another file", data["error"])
|